An automated pipeline for transcribing iMessage voice memos and analyzing images within Openclaw Skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install imsg-media
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install imsg-media using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is imsg-media?
imsg-media is a specialized utility designed to bridge the gap between Apple's Messages.app and AI-driven workflows. It allows agents to access the local iMessage database on macOS to retrieve multimedia attachments that are otherwise difficult to process. By integrating Silicon Flow ASR for high-fidelity audio transcription and utilizing vision models for image analysis, this skill transforms raw media into actionable data. It is a critical component for developers using Openclaw Skills who need to interact with voice notes, screenshots, and photos received via iMessage or SMS.
imsg-media Use Cases
- Transcribing voice memos into text for quick search and documentation.
- Extracting text from screenshots or images via OCR for data entry.
- Identifying the contents of photos sent via iMessage to provide contextual responses.
- Converting HEIC images from iPhones into web-compatible formats automatically.
- Retrieving historical media attachments from specific contacts for archival purposes.
How imsg-media Works
- Detects an attachment placeholder or specific user request to process media.
- Identifies the sender's unique handle (email or phone number) from the message envelope.
- Executes a database query against the local Messages chat.db to find recent files.
- Routes audio files (.m4a, .caf, .wav) to the Silicon Flow SenseVoiceSmall model for transcription.
- Routes image files (.jpg, .png, .heic) to the agent's vision model for description or OCR.
- Returns the structured text output or visual summary directly to the user within the Openclaw Skills environment.
imsg-media Setup
To get started, you must grant Full Disk Access to your terminal or application in macOS System Settings. Install the necessary CLI tool:
npm install -g imsg
Configure your API key for audio transcription in your environment file:
echo "SILICON_FLOW_KEY=sk-your-key-here" >> ~/.openclaw/.env
Ensure you have the imsg-media skill directory properly mapped within your Openclaw Skills configuration to allow the agent to execute the python scripts.
imsg-media Data Schema & Taxonomy
The skill produces structured JSON data when fetching attachments, allowing for precise metadata handling.
| Property | Description |
|---|---|
file |
The absolute local path to the attachment file. |
type |
The category of the media, either audio or image. |
identifier |
The sender's contact info used to locate the file. |
transcription |
The resulting text from audio files (when processed). |
analysis |
The visual description or OCR text from image files. |
imsg-media Advanced Features
- Automatic HEIC to PNG conversion using native macOS sips processing.
- Support for legacy Apple .caf voice memo formats.
- Deep history searching with configurable limit parameters to find older attachments.
- One-click 'auto' mode that handles the entire fetch-and-transcribe lifecycle.
- Seamless integration with multi-agent systems using Openclaw Skills for complex media processing pipelines.
SKILL.md
Loading
Related Openclaw Skills
MiniMax MCP
An official MiniMax Model Context Protocol server providing AI-powered web search and sophisticated image understanding capabilities.
Jimeng AI 4.0 Image Generation
A high-performance AI image generation skill leveraging Jimeng AI 4.0 for text-to-image and image-to-image workflows with optional Feishu integration.
Feishu Voice TTS
A streamlined automation skill that converts text to speech and delivers it as a native audio message to Feishu users.
Agent Retro
A systematic workflow for AI agents to perform daily self-reflections, updating core memory and behavioral configurations based on session history.
MistTrack Crypto AML & Risk Analysis Skill
A comprehensive cryptocurrency AML and security analysis tool for AI agents to track transactions and assess address risks across multiple blockchains.
ABIXUS Deterministic Oracle
A high-performance validation layer ensuring consistency and state verification for autonomous agents on the Polygon PoS network.
Featured*
